| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 40.0, | |
| "global_step": 13440, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.813988095238096e-05, | |
| "loss": 2.8945, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.627976190476191e-05, | |
| "loss": 2.0495, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 4.4419642857142854e-05, | |
| "loss": 1.4014, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 4.255952380952381e-05, | |
| "loss": 1.0101, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 4.0699404761904763e-05, | |
| "loss": 0.6316, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 3.883928571428572e-05, | |
| "loss": 0.4292, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 3.697916666666667e-05, | |
| "loss": 0.2596, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 3.511904761904762e-05, | |
| "loss": 0.1828, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 3.325892857142857e-05, | |
| "loss": 0.1367, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 3.1398809523809525e-05, | |
| "loss": 0.0986, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 16.37, | |
| "learning_rate": 2.953869047619048e-05, | |
| "loss": 0.0818, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 2.767857142857143e-05, | |
| "loss": 0.0581, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 2.5818452380952386e-05, | |
| "loss": 0.0502, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 2.3958333333333334e-05, | |
| "loss": 0.0445, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 22.32, | |
| "learning_rate": 2.2098214285714286e-05, | |
| "loss": 0.036, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 23.81, | |
| "learning_rate": 2.023809523809524e-05, | |
| "loss": 0.0291, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "learning_rate": 1.8377976190476192e-05, | |
| "loss": 0.0371, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 26.79, | |
| "learning_rate": 1.6517857142857144e-05, | |
| "loss": 0.0204, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 28.27, | |
| "learning_rate": 1.4657738095238097e-05, | |
| "loss": 0.0181, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 1.2797619047619047e-05, | |
| "loss": 0.0156, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 0.013, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 32.74, | |
| "learning_rate": 9.077380952380953e-06, | |
| "loss": 0.0118, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 34.23, | |
| "learning_rate": 7.217261904761905e-06, | |
| "loss": 0.009, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 0.0079, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "learning_rate": 3.49702380952381e-06, | |
| "loss": 0.0082, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 38.69, | |
| "learning_rate": 1.636904761904762e-06, | |
| "loss": 0.0084, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 13440, | |
| "total_flos": 2.659014067347456e+16, | |
| "train_loss": 0.3552576902189425, | |
| "train_runtime": 12919.7128, | |
| "train_samples_per_second": 10.403, | |
| "train_steps_per_second": 1.04 | |
| } | |
| ], | |
| "max_steps": 13440, | |
| "num_train_epochs": 40, | |
| "total_flos": 2.659014067347456e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |